Automating the search for a patent’s prior art with a full text similarity search

Lea Helmers, Franziska Horn, Franziska Biegler, Tim Oppermann, Klaus Muller

Research output: Contribution to journalArticle

Abstract

More than ever, technical inventions are the symbol of our society’s advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.

Original languageEnglish
Article numbere0212103
JournalPLoS ONE
Volume14
Issue number3
DOIs
Publication statusPublished - 2019 Mar 1

Fingerprint

Patents
arts
Patents and inventions
patents
Art
Natural Language Processing
artificial intelligence
Learning systems
Feature extraction
Processing
Machine Learning
methodology

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Helmers, L., Horn, F., Biegler, F., Oppermann, T., & Muller, K. (2019). Automating the search for a patent’s prior art with a full text similarity search. PLoS ONE, 14(3), [e0212103]. https://doi.org/10.1371/journal.pone.0212103

Automating the search for a patent’s prior art with a full text similarity search. / Helmers, Lea; Horn, Franziska; Biegler, Franziska; Oppermann, Tim; Muller, Klaus.

In: PLoS ONE, Vol. 14, No. 3, e0212103, 01.03.2019.

Research output: Contribution to journalArticle

Helmers, L, Horn, F, Biegler, F, Oppermann, T & Muller, K 2019, 'Automating the search for a patent’s prior art with a full text similarity search', PLoS ONE, vol. 14, no. 3, e0212103. https://doi.org/10.1371/journal.pone.0212103
Helmers, Lea ; Horn, Franziska ; Biegler, Franziska ; Oppermann, Tim ; Muller, Klaus. / Automating the search for a patent’s prior art with a full text similarity search. In: PLoS ONE. 2019 ; Vol. 14, No. 3.
@article{58adf38843554b8f87a8819cf8896f41,
title = "Automating the search for a patent’s prior art with a full text similarity search",
abstract = "More than ever, technical inventions are the symbol of our society’s advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.",
author = "Lea Helmers and Franziska Horn and Franziska Biegler and Tim Oppermann and Klaus Muller",
year = "2019",
month = "3",
day = "1",
doi = "10.1371/journal.pone.0212103",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Automating the search for a patent’s prior art with a full text similarity search

AU - Helmers, Lea

AU - Horn, Franziska

AU - Biegler, Franziska

AU - Oppermann, Tim

AU - Muller, Klaus

PY - 2019/3/1

Y1 - 2019/3/1

N2 - More than ever, technical inventions are the symbol of our society’s advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.

AB - More than ever, technical inventions are the symbol of our society’s advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.

UR - http://www.scopus.com/inward/record.url?scp=85062412222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062412222&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0212103

DO - 10.1371/journal.pone.0212103

M3 - Article

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e0212103

ER -